Computer Science · Columbia University

Arvind
Raghavan

I am a fourth-year PhD student in Computer Science at Columbia University, supervised by Elias Bareinboim in the Causal AI Lab.

Email Publications CV
LinkedIn Scholar GitHub
Portrait of Arvind Raghavan
Research

My research interests are

  • Causal inference
  • Agent foundations
  • Algorithmic fairness
  • AI safety

I am particularly interested in the science of counterfactuals: testing how models ask and answer “what if” questions. My work involves demonstrating that counterfactual reasoning plays an integral role in fairness, robustness and emergent agency in AI systems.

Selected work

Publications

Google Scholar
  1. 2026
    Preprint

    CoBe: Counterfactual Benchmark for Text Editing

    Arvind Raghavan, Inwoo Hwang, Shreyas Havaldar, Kai-Zhan Lee, Aurghya Maiti, Yushu Pan, Jeffrey Wu, Mingxuan Li, Elias Bareinboim

  2. 2026
    ICML

    Causal Identification from Counterfactual Data: Completeness and Bounding Results

    Arvind Raghavan, Elias Bareinboim

  3. 2025
    ICLR Spotlight · Top 3.6%

    Counterfactual Realizability

    Arvind Raghavan, Elias Bareinboim

    Spotlight award: top 3.6% of 11,373 submissions, by reviewer score.

  4. 2023
    AAAI · EAAI

    A Dataset for Learning University STEM Courses at Scale and Generating Questions at a Human Level

    Iddo Drori, Sarah Zhang, Zad Chin, Reece Shuttleworth, Albert Lu, Linda Chen, Bereket Birbo, Michele He, Pedro Lantigua, Sunny Tran, Gregory Hunter, Bo Feng, Newman Cheng, Roman Wang, Yann Hicke, Saisamrit Surbehera, Arvind Raghavan, Alexander Siemenn, Nikhil Singh, Jayson Lynch, Avi Shporer, Nakul Verma, Tonio Buonassisi, Armando Solar-Lezama

  5. 2023
    CVPR · GCV Workshop

    Text to Graphics by Program Synthesis with Error Correction on Precise, Procedural, and Simulation Tasks

    Ivan Nikitovic, Trisha Anil, Showndarya Madhavan, Arvind Raghavan, Zad Chin, Alexander E Siemenn, Saisamrit Surbehera, Yann Hicke, Ed Chien, Ori Kerret, Ven Commerce, Tonio Buonassisi, Armando Solar-Lezama, Iddo Drori

  6. 2022
    NeurIPS Workshop Oral Presentation

    Human Evaluation of Text-to-Image Models on a Multi-Task Benchmark

    Vitali Petsiuk, Alexander E Siemenn, Saisamrit Surbehera, Zad Chin, Keith Tyser, Gregory Hunter, Arvind Raghavan, Yann Hicke, Bryan A Plummer, Ori Kerret, Tonio Buonassisi, Kate Saenko, Armando Solar-Lezama, Iddo Drori

  7. 2022
    NeurIPS · ML Safety Workshop

    Avoiding Calvinist Decision Traps Using Structural Causal Models

    Arvind Raghavan